NanoCode012
|
8e46c0fb0d
|
Refactor duplicate code between Prompter and Pygmalion
|
2023-05-31 02:53:53 +09:00 |
|
NanoCode012
|
9c6750a075
|
Lint wandb
|
2023-05-31 02:53:53 +09:00 |
|
NanoCode012
|
c2dbf2c526
|
Lint validation
|
2023-05-31 02:53:53 +09:00 |
|
NanoCode012
|
e6b57decbd
|
Lint tokenization
|
2023-05-31 02:53:53 +09:00 |
|
NanoCode012
|
fe1f4c4e7d
|
Lint schedulers
|
2023-05-31 02:53:53 +09:00 |
|
NanoCode012
|
633ff2150f
|
Lint dict
|
2023-05-31 02:53:53 +09:00 |
|
NanoCode012
|
5d86137f70
|
Lint prompt_tokenizers
|
2023-05-31 02:53:53 +09:00 |
|
NanoCode012
|
01c8a333b3
|
Lint pygmalion
|
2023-05-31 02:53:53 +09:00 |
|
NanoCode012
|
1645a4ddd5
|
Lint creative_acr
|
2023-05-31 02:53:53 +09:00 |
|
NanoCode012
|
145b060cbe
|
Lint alpaca_instruct
|
2023-05-31 02:53:53 +09:00 |
|
NanoCode012
|
8cc0aadcb8
|
Lint alpaca_chat
|
2023-05-31 02:53:53 +09:00 |
|
NanoCode012
|
6abb7f6a16
|
Lint datasets
|
2023-05-31 02:53:53 +09:00 |
|
NanoCode012
|
de2406c488
|
Lint convert.py
|
2023-05-31 02:53:53 +09:00 |
|
NanoCode012
|
ddb86ea821
|
Lint trainer.py
|
2023-05-31 02:53:53 +09:00 |
|
NanoCode012
|
f4e5d86268
|
Lint models.py
|
2023-05-31 02:53:23 +09:00 |
|
NanoCode012
|
69722aeef4
|
Remove fixme disable
|
2023-05-31 02:53:23 +09:00 |
|
NanoCode012
|
5658717dbd
|
Remove disable too many arg
|
2023-05-31 02:53:23 +09:00 |
|
NanoCode012
|
e8717d3bef
|
Remove disable
|
2023-05-31 02:53:23 +09:00 |
|
NanoCode012
|
5062eca069
|
Lint callbacks.py
|
2023-05-31 02:53:23 +09:00 |
|
NanoCode012
|
cb4f0e9342
|
Lint prompters.py
|
2023-05-31 02:53:23 +09:00 |
|
NanoCode012
|
4c0eddb3f8
|
Refactor
|
2023-05-31 02:53:23 +09:00 |
|
NanoCode012
|
1c60c10e00
|
Lint flash_attn.py
|
2023-05-31 02:53:23 +09:00 |
|
NanoCode012
|
903ea3080d
|
Fix lint
|
2023-05-31 02:53:23 +09:00 |
|
NanoCode012
|
cb7cd3429f
|
Fix data.py lint
|
2023-05-31 02:53:23 +09:00 |
|
NanoCode012
|
392dfd9b07
|
Lint and format
|
2023-05-31 02:53:22 +09:00 |
|
Wing Lian
|
e65aeedce7
|
fix relative path for fixtures
|
2023-05-30 10:38:20 -04:00 |
|
Wing Lian
|
21c8e2deab
|
refactor conversation plucking in sharegpt
|
2023-05-28 14:36:33 -04:00 |
|
Wing Lian
|
1c33eb88a7
|
new hf_use_auth_token setting so login to hf isn't required
|
2023-05-28 13:08:49 -04:00 |
|
NanoCode012
|
52dd92a0cd
|
Feat: Update validate_config and add tests
|
2023-05-29 00:25:54 +09:00 |
|
NanoCode012
|
7bf2069afd
|
Apply black formatter
|
2023-05-28 23:14:04 +09:00 |
|
NanoCode012
|
56f9ca5709
|
refactor: fix previous refactors
|
2023-05-28 23:06:10 +09:00 |
|
NanoCode012
|
8bd7a49cd7
|
Refactor to use DictDefault instead
|
2023-05-28 23:06:10 +09:00 |
|
NanoCode012
|
18d41cee4a
|
Add DictDefault
|
2023-05-28 23:06:10 +09:00 |
|
NanoCode012
|
bdfe7c9201
|
Convert attrdict to addict
|
2023-05-28 23:06:10 +09:00 |
|
Wing Lian
|
0d4a7f4c04
|
Merge pull request #67 from OpenAccess-AI-Collective/refactor-tokenizer-load
load the tokenizer seperately from the model
|
2023-05-28 08:49:34 -04:00 |
|
NanoCode012
|
782996d94a
|
Merge pull request #86 from OpenAccess-AI-Collective/NanoCode012-warning-remote-code
Feat: Add warning for `trust_remote_code`
|
2023-05-28 01:29:35 +09:00 |
|
NanoCode012
|
9ac1884323
|
Fix: Remove base class inherit for CompletionPrompter
|
2023-05-28 00:51:35 +09:00 |
|
NanoCode012
|
2824423d10
|
Add warning for trust_remote_code
|
2023-05-28 00:46:56 +09:00 |
|
Wing Lian
|
147241ca66
|
Merge branch 'main' into refactor/rename-4b-to-gptq
|
2023-05-27 09:37:52 -04:00 |
|
Wing Lian
|
4c906339f7
|
fix auto linear modules for lora w/o any set already
|
2023-05-27 08:49:43 -04:00 |
|
Wing Lian
|
4c500f5830
|
checking for False is not sufficent for NoneType/unset configs
|
2023-05-27 08:43:48 -04:00 |
|
Thytu
|
dd0065773a
|
refactor(param): rename load_4bit config param by gptq
Signed-off-by: Thytu <vdmatos@gladia.io>
|
2023-05-27 12:36:03 +00:00 |
|
Wing Lian
|
ca1bb92337
|
Update src/axolotl/utils/models.py
Co-authored-by: NanoCode012 <kevinvong@rocketmail.com>
|
2023-05-26 17:51:24 -04:00 |
|
Wing Lian
|
933e970cb5
|
Update src/axolotl/utils/models.py
Co-authored-by: NanoCode012 <kevinvong@rocketmail.com>
|
2023-05-26 17:51:17 -04:00 |
|
NanoCode012
|
ec3c0314bf
|
Merge pull request #65 from NanoCode012/feat/target-linear
Feat: Add `cfg.lora_target_linear`
|
2023-05-26 22:39:38 +09:00 |
|
NanoCode012
|
fe0e69f4f9
|
Fix recommendation condition
|
2023-05-26 22:19:50 +09:00 |
|
Wing Lian
|
32e6fe9286
|
load the tokenizer seperately from the model
|
2023-05-26 07:29:35 -04:00 |
|
NanoCode012
|
919623793a
|
Add cfg.lora_target_linear
|
2023-05-26 14:32:30 +09:00 |
|
Wing Lian
|
a5bf838685
|
add logging and make sure model unloads to float16
|
2023-05-26 00:09:55 -04:00 |
|
Wing Lian
|
a4f12415a0
|
update readme and add typehints
|
2023-05-25 23:10:11 -04:00 |
|